Table 4.

Comparison between the inter-method intraclass correlation coefficients from the z-DWI and s-DWI sets.

Parameter	Inter-method intraclass correlation coefficient
	s-apparent diffusion coefficient (ADC)b50 vs. z-ADC	s-ADCb1000 vs. z-ADC	s-ADCb1500 vs. z-ADC
Reader 1
Peripheral zone (n = 10)	0.87 (0.76–0.98)	0.99 (0.99–1.00)	0.99 (0.94–1.00)
Transitional zone (n = 10)	0.78 (0.58–0.98)	0.98 (0.87–1.00)	0.95 (0.73–0.99)
Benign lesion (n = 50)	0.86 (0.74–0.99)	0.98 (0.94–1.00)	0.98 (0.95–0.99)
Malignant lesion (n = 50)	0.89 (0.76–0.95)	0.90 (0.88–0.98)	0.88 (0.74–0.95)
Reader 2
Peripheral zone (n = 10)	0.81 (0.61–0.99)	0.99 (0.97–1.00)	0.98 (0.88–1.00)
Transitional zone (n = 10)	0.78 (0.58–0.98)	0.99 (0.93–1.00)	0.97 (0.76–1.00)
Benign lesion (n = 50)	0.86 (0.73–0.99)	0.98 (0.95–0.99)	0.97 (0.93–0.99)
Malignant lesion (n = 50)	0.82 (0.70–0.94)	0.88 (0.72–0.95)	0.88 (0.72–0.95)

z-ADC, ADC map derived from zoomed field-of view (FOV) diffusion-weighted imaging and all the available b-values (b = 50, 1,000, and 1,500 s/mm²); s-ADC_b50, ADC map synthesized using our proposed deep learning framework with input from full FOV diffusion-weighted imaging (f-DWI) (b = 50 s/mm²); s-ADC_b1000, ADC map synthesized using our proposed deep learning framework with input from f-DWI (b = 1,000 s/mm²); s-ADC_b1500, ADC map synthesized using our proposed deep learning framework with input from f-DWI (b = 1500 s/mm²).